Zenity for Claude Tag
Claude Tag turns Claude into a shared teammate inside Slack, wired to your team's tools, data, and codebases, and delegated to by anyone in the channel. Zenity gives security teams the visibility, boundaries, and runtime protection to let it thrive with confidence.
Zenity Is Built for the Way Claude Tag Actually Works
See everything Claude Tag is wired to
One record per workspace: the channels it's active in, the people invoking it, and every connector, MCP server, and skill in use.
Set boundaries per channel
Restrict @Claude to the skills, connectors, and MCP servers that have been reviewed for that channel, and stop mutating or irreversible tool calls inline.
Stop injected instructions before they act
Zenity taints a session the moment untrusted content enters it, and evaluates the next action before it completes, even when nothing else looks unusual.
One Entity per Workspace, Everything It Touches in a Single Record
Claude Tag appears in Zenity as one entity per Slack workspace. Security teams get a centralized view of the channels where it operates, the employees using it, and the connectors, credentials, MCP servers, and skill invoked. Activity across scheduled runs and ad hoc requests rolls into a single timeline, with each step tied back to its channel and the Slack author who triggered it.
- Workspace inventory: Channels, users, connectors, credentials, MCP servers, and skills in use, in one place.
- Unified activity timeline: Every run, scheduled or on-demand, correlated to its channel and requester.
- Taint tracking: Each session carries a running record of the untrusted content it has touched.
Know every Claude Tag deployment. Maintain a continuous inventory of every workspace, channel, connector, and credential Claude Tag leverages, kept current as usage grows.
Boundaries Scoped to the Channel, Not Just the Agent
Boundaries apply to Claude Tag exactly as they do to every other agent Zenity governs, scoped per channel. Restrict @Claude in a given channel to the skills, MCP servers, and connectors that have already been reviewed, and stop mutating or irreversible tool calls before they run. Teams keep moving at the speed they want; security keeps its controls without becoming the gate.
- Per-channel policy: Different channels can carry different levels of trust and access.
- Reviewed-only extensions: Only approved skills, connectors, and MCP servers are reachable.
- Inline interception: Mutating or irreversible tool calls are stopped before completion, not logged after the fact.
Define what it's allowed to do. Channel-scoped boundaries on skills, MCP servers, and connectors, with mutating or irreversible actions stopped before they run.
Runtime Protection When an Instruction Is Designed To Slip Through
When Claude Tag reads a crafted instruction hidden inside a support ticket, a document, or a message, Zenity taints the session on ingest and evaluates the next action before it completes. That holds even when nothing in the chain looks inherently wrong: the connector worked as intended, the agent did nothing unusual, and the identity behind the request held permission. Blocking the action contains the blast radius and hands security the full picture of what happened and how it was averted.
- Incident synthesis: Related findings are chained into a single incident, not scattered alerts.
- Full agent trace: Every turn, tool call, and taint that led to the flagged action, in order.
- Evidence, not just a block: What happened, who was involved, and how the breach was contained.
Stop the action, not just the alert. Session tainting and inline evaluation catch injected instructions at the moment they'd otherwise turn into a real action.
Everything Enterprises Need To Turn Claude Tag On With Confidence
Trusted by Forward-Looking Security Leaders
“With Zenity we were able to build a program to remediate existing vulnerabilities with a product that relies on self service and auto-fix so we can scale.”
Existing vulnerabilities remediated within 4 months with 2 FTEs
Tenant grew over 12 months
“We needed a way to partner with the business. Zenity gives us confidence to continue enabling our employees to innovate with AI Agents and applications.”
People developing these systems are not professional developers
Instances of agents and apps that were shared across the entire org
"Zenity provided a preventative layer to proactively reduce security violations of our Agentic AI use. As a result, we saw tremendous growth in cross-departmental adoption of AI Agents."
Reduction in security violations
High-risk violations automatically remediated
"With Zenity, we identified and managed risks from a huge attack surface containing over-shared resources that had access to sensitive data, DLP bypass routes, and misconfigured AI Agents."
Risk reduction across the tenant containing 150k+ total resources
Growth in agent, app, and automation volume
“With Zenity we were able to build a program to remediate existing vulnerabilities with a product that relies on self service and auto-fix so we can scale.”
Existing vulnerabilities remediated within 4 months with 2 FTEs
Tenant grew over 12 months
“We needed a way to partner with the business. Zenity gives us confidence to continue enabling our employees to innovate with AI Agents and applications.”
People developing these systems are not professional developers
Instances of agents and apps that were shared across the entire org
"Zenity provided a preventative layer to proactively reduce security violations of our Agentic AI use. As a result, we saw tremendous growth in cross-departmental adoption of AI Agents."
Reduction in security violations
High-risk violations automatically remediated
"With Zenity, we identified and managed risks from a huge attack surface containing over-shared resources that had access to sensitive data, DLP bypass routes, and misconfigured AI Agents."
Risk reduction across the tenant containing 150k+ total resources
Growth in agent, app, and automation volume
“With Zenity we were able to build a program to remediate existing vulnerabilities with a product that relies on self service and auto-fix so we can scale.”
Existing vulnerabilities remediated within 4 months with 2 FTEs
Tenant grew over 12 months
“We needed a way to partner with the business. Zenity gives us confidence to continue enabling our employees to innovate with AI Agents and applications.”
People developing these systems are not professional developers
Instances of agents and apps that were shared across the entire org
"Zenity provided a preventative layer to proactively reduce security violations of our Agentic AI use. As a result, we saw tremendous growth in cross-departmental adoption of AI Agents."
Reduction in security violations
High-risk violations automatically remediated
"With Zenity, we identified and managed risks from a huge attack surface containing over-shared resources that had access to sensitive data, DLP bypass routes, and misconfigured AI Agents."
Risk reduction across the tenant containing 150k+ total resources
Growth in agent, app, and automation volume
Analyst Recognition & Research Coverage
Frequently Asked Questions
Claude Tag is Anthropic's shared-agent experience for Slack: instead of a personal assistant, Claude operates as a teammate inside a channel that anyone can delegate to with an @-mention, wired to the team's connected tools, data, and codebases.
Claude Tag holds the team's standing access rather than one person's. It doesn't validate who's asking or question intent, so a single crafted instruction, buried in a ticket, document, or message, can act with the agent's full access rather than just affecting one person's session.
Yes. Zenity for Claude Tag is available to Zenity customers with the appropriate administrative permissions. If you're already using Zenity, your account team can help add this integration to your existing setup.
Zenity connects to your Slack workspace and Claude Tag deployment to begin surfacing inventory, applying boundaries, and monitoring for runtime threats. Setup looks like:
- Connect your Slack workspace within the Zenity platform.
- Confirm the channels and connectors where Claude Tag is active.
- Define boundaries for the skills, MCP servers, and connectors Claude Tag can use per channel.
- Zenity begins surfacing activity and enforcing policy immediately.
For additional detail, Zenity customers can view step-by-step documentation in the customer portal.
Anthropic has announced plans to bring Claude Tag to Microsoft Teams. Zenity's agent-layer approach is built to extend to new surfaces as Anthropic ships them; contact your account team for current availability.
Turn on Claude Tag with confidence
Get unified visibility, boundaries, and real-time protection over shared Claude agents across your Slack workspace.
Get a Demo